Volume, Variety and Velocity are the three dimensions that have definitely changed the tools we need to store and process Big Data effectively, giving rise to NoSQL systems for faster data access, better scalability and higher flexibility. While NoSQL systems have proven their efficiency to handle Big Data, it is still an unsolved problem how the automatic storage of Big Data in NoSQL systems could be done. One solution for addressing this problem is to model Big Data, and then define mapping rules towards the physical level. This paper proposes an automatic MDA-based approach that translates conceptual models expressed using the Unified Modeling Language (UML) into NoSQL physical models. Our approach rely on an intermediate logical model compatible with column, document and graph oriented systems which allows to choose the system type that suits the best with business rules and technical constraints.