Osteoarthritis (OA) is a slowly progressing disease characterized clinically by pain, deformity, enlargement of the joints, and limitation of motion. OA causes, among other changes, loss in cartilage volume that increases as the disease progresses. OA is a complex disease and objective documentation of disease progression or response to treatment is challenging. Approximately 27 million adults age 25 and older have clinically diagnosed OA; however, cartilage loss with disease progression is small and localized to sub-regions of the cartilage. Detection of these changes is challenging and manual methods are tedious and error prone. Magnetic resonance imaging (MRI) is a non-invasive modality that provides high-resolution, 3-dimensional images with high contrast between cartilage and the surrounding anatomy. Highly accurate measures of cartilage volume, and thickness (global and local) can be extracted from morphological MR images. The focus of this research is on development of accurate tools to quantify the small and localized changes in cartilage morphology to facilitate comparisons between patient cohorts with varying degrees of OA as well as to track longitudinal changes (normal progression and response to treatment). The application area is the femoral cartilage but the methodology can be readily extended to the patellar and tibial cartilage. We explored a fast, readily implementable algorithm called the 'Demons Algorithm'. We implemented and compared the registration accuracy of four variants of the algorithm on cartilage image volumes. The registration algorithms were also evaluated for the accuracy of the average Jacobians. Evaluation was performed on 36 subjects using the baseline and later time point images acquired after 12 months. The symmetric evolved demons algorithm provided the best in registration accuracy evaluated using quantitative metrics of mean squared error and voxel overlap. The average Jacobian of the cartilage was compared to the ratio of volume change for validation. The symmetric simple demons and symmetric evolved demons performed equally well in terms of the Jacobians. The techniques developed here will be used, in future studies, to explore differences in cohorts segregated by disease severity and correlation of local changes to clinical variables.