Since the complex outliers caused by the background and non-rigid deformation, image registration remains a challenging task. This paper proposes a new method for image registration, which is robust to the transformations with rotation, scale and translation. Our method is under the general Iterative Closet Point (ICP) framework which contains two main parts: finding the corresponding points and updating transformation parameters. In our method, to be robust to outliers, Best-Buddies Pairs (BBPs) are used as similarity measure between two images to obtain the corresponding points. While, in order to be invariant to scale transformation, Scaling ICP is employed to update transformation parameters. Besides the image registration, we also apply the method for object tracking in video sequences. Experimental results demonstrate the effectiveness and efficiency of the proposed method.