The multi-modal image registration is a complex task in the medical domain. This task requires usually several manual interventions by the user/expert of the domain to adjust the image registration parameters properly to the characteristics of the processed image data. For this aim, the user needs to extract the relevant information from the image data and their metainformation. In this paper, we propose a novel architecture for a smart fully automatic multimodal registration process. This architecture is based on a MAPE-K loop inspired by the architecture of autonomous systems.