Closed-form solutions are traditionally used in computer vision for estimating rigid body transformations. Here we suggest an iterative solution for estimating rigid body transformations and prove its global convergence. We show that for a number of applications involving repeated estimations of rigid body transformations, an iterative scheme is preferable to a closed-form solution. We illustrate this experimentally on two applications, 3D object tracking and image registration with Iterative Closest Point. Our results show that for those problems using an iterative and continuous estimation process is more robust than using many independent closed-form estimations.