We are developing an automated 3D change detection system which accurately registers medical imagery (e.g., MRI or CT) of the same patient from different times for diagnosing pathologies, monitoring treatment, and tracking tissue changes. The system employs a combination of energyminimization registration techniques to achieve ac~ curate and robust alignment of 3D data sets. The bases for the registration are 3D surfaces extracted from the 3D imagery. Resultant changes in the data are identified by differencing registered normalized intensity images or comparing measurements of the same segmented tissue over time. The contributions of this work are (1) automation the registration process, (2) high registration accuracy, and (3) registration stability in the presence of noise, outliers, and data deviations. We have applied this system to a rigid registration problem, namely head registration for multiple sclerosis change detection, and are exploring other rigid and flexible registration applications.