Information Visualization applications are dealing with fundamental difficulties related to overlap in cognitive models between designers and users, goal ambiguity, and accuracy in search strategies These difficulties are more obvious in applications aimed at reducing information overload by general users, than in applications aimed at visualising scientific data. General users have very likely quite different cognitive reference for approaching an abstract complex task, than designers. This can result in designs which can unintentionally increase information overload by users. In visualisation of scientific data the overlap of cognitive reference between specialists and designs is very likely much higher, but we need methods which can facilitate data exploration in real-time interaction. One possibility to facilitate exploration in a more or less systematic way is by means of metaphors which can support human perception in searching for patterns.