We describe the extension to multiple datasets of a coherent method for the search of continuous gravitational wave signals, based on the computation of 5-vectors. In particular, we show how to coherently combine different datasets belonging to the same detector or to different detectors. In the latter case the coherent combination is the way to have the maximum increase in signal-to-noise ratio. If the datasets belong to the same detector the advantage comes mainly from the properties of a quantity called {it coherence} which is helpful (in both cases, in fact) in rejecting false candidates. The method has been tested searching for simulated signals injected in Gaussian noise and the results of the simulations are discussed.