The following paper proposes a methodological tool to use design patterns in Big Data architectures. The adequacy to a Big Data architecture is not a simple task but, as it happens with software, it is possible to use patterns that are repeated depending on what kind of solutions are needed. This tool executes a series of given information and as a result proposes design prototypes that well in a later simulation tool can be trained to review their efficiency and performance. It should be noted that in this work it is intended to give this model and to be able to validate it in a following Doctoral Thesis.