Metabolite identification is a significant bottleneck in untargeted metabolomics studies. While existing pipelines, such as XCMS Online, allow for rapid determination of significant features, annotation of metabolites, and mapping metabolites to biological pathways, these preliminary annotations have low confidence due to relying on exact mass alone. While other methodologies exist to improve confidence in identification through formula prediction and MS/MS fragment matching, these methods often require manual analysis of individual features, which can be time-consuming in studies with hundreds or thousands of dysregulated features. To improve the efficiency of metabolite identification, a pipeline, MZWork, was developed to annotate metabolic features using isotope ratio-based formula identification and MS/MS-based structural identification of LC-MS experiments in parallel using MS-FINDER and MS-DIAL. The highest-scoring annotations are compiled and input into an app to perform statistical analysis to determine dysregulated features. Features can be filtered on statistical significance, degree of dysregulation, overall abundance, and quality of formula and structure matches. MZWork then visualizes filtered features based on m/z and retention time values, as well as visualization of both isotope ratio and MS/MS matches for selected features. Quality of the metabolite identifications was assessed using a mouse intestine dataset and comparing this workflow to XCMS Online dysregulated features with predicted metabolite identifications using XCMS Online agrees with the highest-scoring formula from MS-FINDER in 33% of features, mismatched in 12%, and the remaining having no isotope pattern to match. Additionally, 19% of XCMS predicted metabolites agree with the highest-scoring MS/MS compound matches in MZWork. In the bile acid biosynthesis pathway XCMS predicted 7 dysregulated metabolites, all of which had matching formula identifications on MS-FINDER, and 3 metabolites were verified using MS/MS. Additionally, 5 dysregulated metabolites were identified by MS-FINDER based on the highest-scoring formula match that were not identified using XCMS Online. This workflow allows for rapid metabolite identification to supplement preliminary results from XCMS Online, facilitating insight into biological mechanisms.